Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
DeepSeek V3.2 (Thinking)
68
Winner · 2/8 categoriesQwen3.5-35B-A3B
67
5/8 categoriesDeepSeek V3.2 (Thinking)· Qwen3.5-35B-A3B
Pick DeepSeek V3.2 (Thinking) if you want the stronger benchmark profile. Qwen3.5-35B-A3B only becomes the better choice if coding is the priority or you need the larger 262K context window.
DeepSeek V3.2 (Thinking) finishes one point ahead overall, 68 to 67. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
DeepSeek V3.2 (Thinking)'s sharpest advantage is in agentic, where it averages 69.4 against 50.5. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 71% to 40.5%. Qwen3.5-35B-A3B does hit back in coding, so the answer changes if that is the part of the workload you care about most.
Qwen3.5-35B-A3B gives you the larger context window at 262K, compared with 128K for DeepSeek V3.2 (Thinking).
BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.
Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.
| Benchmark | DeepSeek V3.2 (Thinking) | Qwen3.5-35B-A3B |
|---|---|---|
| AgenticDeepSeek V3.2 (Thinking) wins | ||
| Terminal-Bench 2.0 | 71% | 40.5% |
| BrowseComp | 70% | 61% |
| OSWorld-Verified | 67% | 54.5% |
| tau2-bench | — | 81.2% |
| CodingQwen3.5-35B-A3B wins | ||
| HumanEval | 79% | — |
| SWE-bench Verified | 48% | 69.2% |
| LiveCodeBench | 45% | 74.6% |
| SWE-bench Pro | 58% | — |
| Multimodal & GroundedQwen3.5-35B-A3B wins | ||
| MMMU-Pro | 66% | 75.1% |
| OfficeQA Pro | 77% | — |
| ReasoningDeepSeek V3.2 (Thinking) wins | ||
| MuSR | 81% | — |
| BBH | 86% | — |
| LongBench v2 | 78% | 59% |
| MRCRv2 | 78% | — |
| ARC-AGI-2 | 4% | — |
| KnowledgeQwen3.5-35B-A3B wins | ||
| MMLU | 87% | — |
| GPQA | 85% | 84.2% |
| SuperGPQA | 83% | 63.4% |
| MMLU-Pro | 73% | 85.3% |
| HLE | 22% | — |
| FrontierScience | 77% | — |
| SimpleQA | 83% | — |
| Instruction FollowingQwen3.5-35B-A3B wins | ||
| IFEval | 85% | 91.9% |
| MultilingualQwen3.5-35B-A3B wins | ||
| MGSM | 84% | — |
| MMLU-ProX | 79% | 81% |
| Mathematics | ||
| AIME 2023 | 87% | — |
| AIME 2024 | 89% | — |
| AIME 2025 | 88% | — |
| HMMT Feb 2023 | 83% | — |
| HMMT Feb 2024 | 85% | — |
| HMMT Feb 2025 | 84% | — |
| BRUMO 2025 | 86% | — |
| MATH-500 | 84% | — |
DeepSeek V3.2 (Thinking) is ahead overall, 68 to 67. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 71% and 40.5%.
Qwen3.5-35B-A3B has the edge for knowledge tasks in this comparison, averaging 79.3 versus 65.9. Inside this category, SuperGPQA is the benchmark that creates the most daylight between them.
Qwen3.5-35B-A3B has the edge for coding in this comparison, averaging 72.6 versus 50.7. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
DeepSeek V3.2 (Thinking) has the edge for reasoning in this comparison, averaging 60.1 versus 59. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
DeepSeek V3.2 (Thinking) has the edge for agentic tasks in this comparison, averaging 69.4 versus 50.5. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Qwen3.5-35B-A3B has the edge for multimodal and grounded tasks in this comparison, averaging 75.1 versus 71. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Qwen3.5-35B-A3B has the edge for instruction following in this comparison, averaging 91.9 versus 85. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Qwen3.5-35B-A3B has the edge for multilingual tasks in this comparison, averaging 81 versus 80.8. Inside this category, MMLU-ProX is the benchmark that creates the most daylight between them.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.